论文标题
计划在线持续持续学习
Schedule-Robust Online Continual Learning
论文作者
论文摘要
持续学习（CL）算法从非平稳数据流中学习。非平稳性是由某些时间表模拟的，该时间表确定数据随时间的呈现方式。大多数当前的方法在时间表上做出了强大的假设，并且在不满足此类要求时具有不可预测的性能。因此，CL中的一个关键挑战是在相同的基础数据上设计可靠的方法，因为在实际情况下，时间表通常是未知且动态的。在这项工作中，我们介绍了CL的时间表的概念，并在充满挑战的在线课堂开发环境中满足了这种理想的财产的新颖方法。我们还对CL提出了一个新的视角，作为学习时间表的预测器的过程，然后仅使用重播数据来调整预测变量。从经验上讲，我们证明我们的方法的表现优于基准上的现有方法，用于图像分类。
A continual learning (CL) algorithm learns from a non-stationary data stream. The non-stationarity is modeled by some schedule that determines how data is presented over time. Most current methods make strong assumptions on the schedule and have unpredictable performance when such requirements are not met. A key challenge in CL is thus to design methods robust against arbitrary schedules over the same underlying data, since in real-world scenarios schedules are often unknown and dynamic. In this work, we introduce the notion of schedule-robustness for CL and a novel approach satisfying this desirable property in the challenging online class-incremental setting. We also present a new perspective on CL, as the process of learning a schedule-robust predictor, followed by adapting the predictor using only replay data. Empirically, we demonstrate that our approach outperforms existing methods on CL benchmarks for image classification by a large margin.
